Convectively-induced turbulence (CIT) is one of several threats that requires aircraft to avoid thunderstorms in order to mitigate the risk of passenger injury or aircraft damage. Current FAA thunderstorm avoidance guidelines proscribe flight within 20 or 30 nautical miles of a thunderstorm, above thunderstorm tops or beneath anvils. In practice, interpretation of these guidelines is subjective and limited by available weather information, and the guidelines may make large regions of airspace unavailable to aircraft on days of widespread convection. An automated turbulence product that makes use of radar, lightning, satellite, numerical weather model and convective nowcast data to objectively diagnose the likelihood of turbulence in the near-storm environment could provide valuable strategic and tactical decision support to pilots, dispatchers and air traffic controllers.

The advent of automated, quantitative turbulence reports from commercial aircraft has made it possible to use machine learning techniques to help develop such diagnostics. This paper describes the use of random forests--collections of weakly-correlated decision trees--to help establish relationships between storm features and aircraft turbulence that were then used to develop a fuzzy logic predictive algorithm for turbulence intensity near thunderstorms. Values from the RUC model were interpolated to the aircraft position, and a spatial “dartboard” oriented relative to the mean wind direction was used to collect data on storm intensity and coverage in a number of regions surrounding the turbulence measurement point. After random forests were trained to learn a predictive algorithm based on these quantities, its behavior was analyzed and a fuzzy logic algorithm was created to perform the turbulence diagnosis in real time. The fuzzy logic predictive algorithm was tuned based on the random forest and then verified using an independent testing set.